Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 8 papers
Filter2

Model risks

Dangerous agent actions3

System type

Models and APIs78AI Agent8coding agent4Embodied systems and robotics3

Layer

Prompt layer4Model layer8Application layer219
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
System type：AI AgentLayer：Model layerClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  4. Evaluation and benchmarksarXiv 2609.39533

    CATCH：面向编码 RL 奖励作弊的可控分析测试台

    构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效

    arXiv
    2609.39533
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen3-4B, Qwen3.5-27B
    AbstractCATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。

    CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.35408

    研究揭示 LLM 交付物修订痕迹导致的无意泄露，并提出 RevLeakBench 基准

    用 RevLeakBench 测量 LLM 交付物修订痕迹的无意泄露

    arXiv
    2609.35408
    Published
    Layer
    Model layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6, GPT-5.5, DeepSeek-V4-Pro and others6
    Abstract修订痕迹让撤回项重新进入交付物。

    修订痕迹指模型按要求删掉或换掉一项后，又在交代这次修改时把它写进给第三方的交付物。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2605.17062

    研究复现五个前沿模型的包名幻觉：跨模型共同幻觉 127 个包名，53 个仍可被注册

    复评前沿模型代码生成中的包名幻觉与抢注攻击面

    arXiv
    2605.17062
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini and others5

    Abstract评估显示前沿模型包幻觉率收窄但威胁仍在，作者识别出跨模型通用攻击面并呼吁联合防御。

    Paper analysisRead analysis
  8. Evaluation and benchmarksarXiv 2604.12447

    HazardArena：面向 VLA 模型的语义安全评测基准

    提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全

    arXiv
    2604.12447
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-OFT, π0, NORA and others4
    Abstractsafe-only 微调提升良性执行，也提升匹配不安全孪生上的危险完成。

    HazardArena 评测 VLA 在运动要求不变时，能否因语义风险而停手。

    Paper analysisRead analysis
You have reached the end